CN113570473B - Equipment fault monitoring method, device, computer equipment and storage medium - Google Patents
Equipment fault monitoring method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113570473B CN113570473B CN202110712688.6A CN202110712688A CN113570473B CN 113570473 B CN113570473 B CN 113570473B CN 202110712688 A CN202110712688 A CN 202110712688A CN 113570473 B CN113570473 B CN 113570473B
- Authority
- CN
- China
- Prior art keywords
- feature vector
- operation data
- equipment
- monitored
- real
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 52
- 238000000034 method Methods 0.000 title claims abstract description 41
- 239000013598 vector Substances 0.000 claims abstract description 275
- 238000000605 extraction Methods 0.000 claims abstract description 49
- 238000004364 calculation method Methods 0.000 claims abstract description 13
- 238000012549 training Methods 0.000 claims description 45
- 230000002159 abnormal effect Effects 0.000 claims description 32
- 238000004590 computer program Methods 0.000 claims description 26
- 238000012423 maintenance Methods 0.000 claims description 12
- 125000004122 cyclic group Chemical group 0.000 claims description 11
- 238000003062 neural network model Methods 0.000 claims description 11
- 230000007613 environmental effect Effects 0.000 claims description 4
- 238000012806 monitoring device Methods 0.000 abstract description 3
- 230000005540 biological transmission Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 206010033799 Paralysis Diseases 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The application relates to an equipment fault monitoring method, an equipment fault monitoring device, computer equipment and a storage medium. The method comprises the following steps: inputting real-time operation data of equipment to be monitored into a preset feature extraction network, and obtaining a high-dimensional feature vector of the real-time operation data; obtaining a prototype feature vector of the equipment to be monitored according to the high-dimensional feature vector of the real-time operation data; the prototype feature vector is the mean value of the normal operation data of the equipment to be monitored, which is expressed in the form of a high-dimensional vector; performing similarity calculation on the prototype feature vector and the high-dimensional feature vector of the real-time operation data to obtain a similarity value between the prototype feature vector and the high-dimensional feature vector of the real-time operation data; and judging whether the equipment to be monitored fails or not based on the similarity value. By adopting the method, the accuracy of fault prediction of the equipment to be monitored can be improved.
Description
Technical Field
The present disclosure relates to the field of equipment fault monitoring technologies, and in particular, to an equipment fault monitoring method, an apparatus, a computer device, and a storage medium.
Background
With the continuous development of the current power system, more and more power distribution rooms are distributed in various areas of cities and villages. Because of the numerous electrical devices and control devices in a power distribution room, professional operation and maintenance personnel are often required to manage the normal operation of the equipment in the power distribution room and to avoid foreign personnel entering the power distribution room. Under unattended conditions, various control devices may produce device failures, resulting in power system damage with serious consequences. Even if the power supply and distribution system is not paralyzed, the power resource waste, the unstable power supply and other consequences can be caused, and the stable operation of the power system is interfered.
In the conventional technology, when detecting a device fault, real-time operation data of the device to be monitored is generally input into a preset fault judgment model to judge, so as to obtain a result of whether the device to be monitored has a fault. The fault judging model is generated by training based on data when equipment to be monitored breaks down as a training set. However, as the number of operation data samples is generally small when equipment fails, the problem that the failure judgment model generated by training generally has low accuracy rate is caused, and the technical problem that the monitoring accuracy rate is low when equipment to be monitored is subjected to failure monitoring is caused.
Disclosure of Invention
In view of the foregoing, it is desirable to provide an apparatus, a device, a computer device, and a storage medium that are capable of improving the accuracy of apparatus fault monitoring.
A method of equipment fault monitoring, the method comprising:
inputting real-time operation data of equipment to be monitored into a preset feature extraction network, and obtaining a high-dimensional feature vector of the real-time operation data; the feature extraction network is obtained based on sample operation data and high-dimensional feature vector training corresponding to the sample operation data;
obtaining a prototype feature vector of the equipment to be monitored according to the high-dimensional feature vector of the real-time operation data; the prototype feature vector is a mean value of normal operation data of the equipment to be monitored, which is expressed in the form of a high-dimensional vector;
performing similarity calculation on the prototype feature vector and the high-dimensional feature vector of the real-time operation data to obtain a similarity value between the prototype feature vector and the high-dimensional feature vector of the real-time operation data;
and judging whether the equipment to be monitored has faults or not based on the similarity value.
In one embodiment, the method further comprises: acquiring operation data of the equipment to be monitored in normal operation within a preset time period, and taking the operation data as sample operation data; extracting features of the sample operation data to obtain a high-dimensional feature vector corresponding to the sample operation data; and training a cyclic neural network model by taking the sample operation data and the high-dimensional feature vector corresponding to the sample operation data as a training set to obtain a feature extraction network.
In one embodiment, the method further comprises: and acquiring a median or average value of the high-dimensional feature vector of the real-time operation data as a prototype feature vector of the equipment to be monitored.
In one embodiment, the method further comprises: and calculating Euclidean distance between the prototype feature vector and the high-dimensional feature vector of the real-time operation data, and taking the Euclidean distance as a similarity value between the prototype feature vector and the high-dimensional feature vector of the real-time operation data.
In one embodiment, the method further comprises: comparing the similarity value with a preset fault threshold value; and if the similarity value exceeds the fault threshold value, judging that the equipment to be monitored is in a normal running state.
In one embodiment, the method further comprises: and if the similarity value does not exceed the fault threshold value, judging that the equipment to be monitored is in an abnormal operation state.
In one embodiment, the method further comprises: and sending the abnormal information of the equipment to be monitored to operation and maintenance personnel, and simultaneously sending out an abnormal alarm.
An equipment failure monitoring apparatus, the apparatus comprising:
the first acquisition module is used for inputting real-time operation data of the equipment to be monitored into a preset feature extraction network to acquire a high-dimensional feature vector of the real-time operation data; the feature extraction network is obtained based on sample operation data and high-dimensional feature vector training corresponding to the sample operation data;
the second acquisition module is used for acquiring the prototype feature vector of the equipment to be monitored according to the high-dimensional feature vector of the real-time operation data; the prototype feature vector is a mean value of normal operation data of the equipment to be monitored, which is expressed in the form of a high-dimensional vector;
the third acquisition module is used for carrying out similarity calculation on the prototype feature vector and the high-dimensional feature vector of the real-time operation data to acquire a similarity value between the prototype feature vector and the high-dimensional feature vector of the real-time operation data;
and the fault monitoring module is used for judging whether the equipment to be monitored has faults or not based on the similarity value.
A computer device comprising a memory storing a computer program and a processor which when executing the computer program performs the steps of:
inputting real-time operation data of equipment to be monitored into a preset feature extraction network, and obtaining a high-dimensional feature vector of the real-time operation data; the feature extraction network is obtained based on sample operation data and high-dimensional feature vector training corresponding to the sample operation data;
obtaining a prototype feature vector of the equipment to be monitored according to the high-dimensional feature vector of the real-time operation data; the prototype feature vector is a mean value of normal operation data of the equipment to be monitored, which is expressed in the form of a high-dimensional vector;
performing similarity calculation on the prototype feature vector and the high-dimensional feature vector of the real-time operation data to obtain a similarity value between the prototype feature vector and the high-dimensional feature vector of the real-time operation data;
and judging whether the equipment to be monitored has faults or not based on the similarity value.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
inputting real-time operation data of equipment to be monitored into a preset feature extraction network, and obtaining a high-dimensional feature vector of the real-time operation data; the feature extraction network is obtained based on sample operation data and high-dimensional feature vector training corresponding to the sample operation data;
obtaining a prototype feature vector of the equipment to be monitored according to the high-dimensional feature vector of the real-time operation data; the prototype feature vector is a mean value of normal operation data of the equipment to be monitored, which is expressed in the form of a high-dimensional vector;
performing similarity calculation on the prototype feature vector and the high-dimensional feature vector of the real-time operation data to obtain a similarity value between the prototype feature vector and the high-dimensional feature vector of the real-time operation data;
and judging whether the equipment to be monitored has faults or not based on the similarity value.
According to the equipment fault monitoring method, the equipment fault monitoring device, the computer equipment and the storage medium, the high-dimensional feature vector of real-time operation data of the equipment to be monitored is obtained through the preset feature extraction network, the prototype feature vector of the equipment to be monitored is obtained according to the high-dimensional feature vector of the real-time operation data, finally the similarity value between the high-dimensional feature vector of the real-time operation data and the prototype feature vector is obtained, and whether the equipment to be monitored has faults is judged based on the similarity value. Compared with the monitoring of the equipment to be monitored by taking the data generated by the training of the training set as the fault judgment model, the prediction accuracy in fault monitoring is improved.
Drawings
FIG. 1 is an application environment diagram of a device fault monitoring method in one embodiment;
FIG. 2 is a flow diagram of a method of device fault monitoring in one embodiment;
FIG. 3 is a schematic diagram illustrating the collection of real-time operational data of a device to be monitored in one embodiment;
FIG. 4 is a flow chart of a feature extraction network generation step in one embodiment;
FIG. 5 is a flow chart of a method for monitoring equipment failure in another embodiment;
FIG. 6 is a schematic diagram of a device fault monitoring apparatus in one embodiment;
fig. 7 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The equipment fault monitoring method provided by the application can be applied to an application environment shown in figure 1. Wherein the terminal 102 communicates with the server 104 via a network. The terminal 102 and the server 104 may each be used separately to perform the device fault monitoring methods provided herein. The terminal 102 and the server 104 may also be configured to cooperatively perform the device fault monitoring methods provided herein. For example, the server 104 is configured to input real-time operation data of a device to be monitored into a preset feature extraction network, and obtain a high-dimensional feature vector of the real-time operation data; the feature extraction network is obtained based on sample operation data and high-dimensional feature vector training corresponding to the sample operation data; obtaining a prototype feature vector of the equipment to be monitored according to the high-dimensional feature vector corresponding to the sample operation data; the prototype feature vector is a mean value of normal operation data of the equipment to be monitored, which is expressed in the form of a high-dimensional vector; performing similarity calculation on the prototype feature vector and the high-dimensional feature vector of the real-time operation data to obtain a similarity value between the prototype feature vector and the high-dimensional feature vector of the real-time operation data; and judging whether the equipment to be monitored has faults or not based on the similarity value.
The terminal 102 may be, but is not limited to, a device including a device to be monitored and a data acquisition device, and the server 104 may be implemented by a stand-alone server or a server cluster formed by a plurality of servers.
In one embodiment, as shown in fig. 2, there is provided an equipment fault monitoring method, which is described by taking an example that the method is applied to the terminal in fig. 1, and includes the following steps:
step 202, inputting real-time operation data of equipment to be monitored into a preset feature extraction network, and obtaining a high-dimensional feature vector of the real-time operation data; the feature extraction network is obtained based on sample operation data and high-dimensional feature vector training corresponding to the sample operation data.
Fig. 3 is a schematic diagram of real-time operation data collection of equipment to be monitored in an embodiment, where the equipment to be monitored includes a power distribution device, a high-low voltage device and a control device. The distribution equipment mainly comprises a transformer box, a PT cabinet, a transformer and the like in a distribution room. The main function of the power distribution equipment is to convert the high voltage of a power transmission line into the low voltage of a user or the industrial power voltage, and shunt the power resources of the power transmission line; the high-low voltage equipment mainly comprises a high-voltage wire inlet cabinet, a high-voltage transmission line, a high-voltage bus-tie cabinet, an isolation grid and the like, and the main purpose of the equipment is to transmit electric energy in a power plant to a near-user side; the control equipment mainly comprises a PLC, a digital control equipment and the like, and mainly controls the power distribution equipment and the high-low voltage equipment to operate stably according to preset control logic.
The real-time operation data comprise electric quantity parameters such as voltage values and current values when the equipment to be monitored operates, environment parameters such as temperature and environment humidity of the equipment to be monitored, which are obtained through various sensors, and operation videos of the equipment to be monitored, which are obtained through a camera device. The data transmission is usually performed in real time in a wired transmission mode and a wireless transmission mode, the wireless transmission mode is, for example, a Long Range Radio (Long Range Radio) technology, and the wired transmission mode includes optical fibers, cables and the like, and the uplink transmission of the data is realized by matching with an industrial transmission protocol.
When the real-time operation data of the equipment to be monitored is input into a preset feature extraction network, the feature extraction network is preset by inputting at least one real-time operation data input value in the operation video of the equipment to be monitored, which is obtained through various sensors, such as voltage value, current value and other electric parameters of the equipment to be monitored, temperature, environmental humidity and other environmental parameters of the equipment to be monitored, and the operation video of the equipment to be monitored, wherein the feature extraction network is usually trained by a circulating neural network.
Step 204, obtaining a prototype feature vector of the equipment to be monitored according to the high-dimensional feature vector of the real-time operation data; the prototype feature vector is a mean value of normal operation data of the equipment to be monitored, which is expressed in the form of a high-dimensional vector.
Specifically, the prototype feature vector of the device to be monitored is obtained according to the high-dimensional feature vector of the real-time operation data, the prototype feature vector is a reference feature vector for judging the operation state of the device to be monitored, and the prototype feature vector is usually obtained by taking the average value of the high-dimensional feature vector of the device to be monitored in the real-time operation data or is set in a preset mode.
And 206, performing similarity calculation on the prototype feature vector and the high-dimensional feature vector of the real-time operation data to obtain a similarity value between the prototype feature vector and the high-dimensional feature vector of the real-time operation data.
Specifically, the similarity value between the prototype feature vector and the high-dimensional feature vector of the real-time operation data is a parameter for characterizing the degree of similarity between the high-dimensional feature vector of the real-time operation data and the prototype feature vector. Various methods for obtaining a similarity value are used to calculate the similarity value according to the prototype feature vector and the high-dimensional feature vector of the real-time operation data, such as calculating the euclidean distance between the prototype feature vector and the high-dimensional feature vector of the real-time operation data, calculating the cosine similarity value between the prototype feature vector and the high-dimensional feature vector of the real-time operation data, or calculating the mahalanobis distance between the prototype feature vector and the high-dimensional feature vector of the real-time operation data.
And step 208, judging whether the equipment to be monitored has faults or not based on the similarity value.
Specifically, since the similarity value between the prototype feature vector and the high-dimensional feature vector of the real-time operation data is a parameter for representing the degree of similarity between the high-dimensional feature vector of the real-time operation data and the prototype feature vector, the higher the similarity value, the closer the prototype feature vector and the high-dimensional feature vector of the real-time operation data are, the more normal the operation of the device to be monitored is proved; the lower the similarity value is, the larger the difference between the prototype feature vector and the high-dimensional feature vector of the real-time operation data is proved, and the higher the probability of abnormal operation state of the equipment to be monitored is.
In the equipment fault monitoring method, the high-dimensional feature vector of the real-time operation data of the equipment to be monitored is obtained through the preset feature extraction network, the prototype feature vector of the equipment to be monitored is obtained according to the high-dimensional feature vector of the real-time operation data, the similarity value between the high-dimensional feature vector of the real-time operation data and the prototype feature vector is finally obtained, and whether the equipment to be monitored has faults or not is judged based on the similarity value. Compared with the monitoring of the equipment to be monitored by taking the data generated by the training of the training set as the fault judgment model, the prediction accuracy in fault monitoring is improved.
In one embodiment, the feature extraction network is obtained by:
acquiring operation data of the equipment to be monitored in normal operation within a preset time period, and taking the operation data as sample operation data;
extracting features of the sample operation data to obtain a high-dimensional feature vector corresponding to the sample operation data;
and training a cyclic neural network model by taking the sample operation data and the high-dimensional feature vector corresponding to the sample operation data as a training set to obtain a feature extraction network.
Specifically, as shown in fig. 4, fig. 4 is a flow chart of a feature extraction network generating step in an embodiment, and operation data of equipment to be monitored in normal operation within a preset time period is selected as sample operation data; the type of the sample operation data comprises at least one of electric quantity parameters such as a voltage value and a current value when equipment to be monitored operates, environment parameters such as the temperature and the environment humidity of the equipment to be monitored, which are acquired through various sensors, and operation videos of the equipment to be monitored, which are acquired through a camera device. Feature extraction of the sample operation data comprises extracting time sequence features and semantic features of the sample operation data, and setting the extracted features into a high-dimensional feature vector form. And finally, taking the sample operation data and the high-dimensional feature vector corresponding to the sample operation data as a training set, training a cyclic neural network model, and taking the trained cyclic neural network model as a feature extraction network.
For example, as shown in fig. 5, fig. 5 is a schematic flow chart of a method for monitoring equipment failure in another embodiment, and the monitoring equipment obtains a video of the equipment to be monitored when the equipment to be monitored normally operates within a preset time period as sample operation data; and then carrying out feature extraction on sample operation data to obtain a high-dimensional feature vector corresponding to a video of the equipment to be monitored in normal operation within a preset time period, and finally training a cyclic neural network model by taking the video of the equipment to be monitored in normal operation within the preset time period and the high-dimensional feature vector corresponding to the video of the equipment to be monitored in normal operation within the preset time period as training sets to obtain a feature extraction network.
In this embodiment, operation data of the device to be monitored during normal operation in a preset time period is obtained and used as sample operation data, feature extraction is performed on the sample operation data, a high-dimensional feature vector corresponding to the sample operation data is obtained, and finally the sample operation data and the high-dimensional feature vector corresponding to the sample operation data are used as training sets to train a cyclic neural network model to obtain a feature extraction network. The method and the device realize the rapid conversion from real-time operation data of the equipment to be monitored to the high-dimensional feature vector, and improve the efficiency of fault monitoring of the equipment to be monitored.
In one embodiment, the obtaining the prototype feature vector of the device to be monitored according to the high-dimensional feature vector of the real-time operation data includes:
and acquiring a median or average value of the high-dimensional feature vector of the real-time operation data as a prototype feature vector of the equipment to be monitored.
Specifically, after the real-time operation data of the equipment to be monitored is input into a preset feature extraction network and the high-dimensional feature vector of the real-time operation data is obtained, the median or average value of the high-dimensional feature vector of the real-time operation data in a preset time range is obtained and is used as a prototype feature vector of the equipment to be monitored.
In this embodiment, the median or average value of the high-dimensional feature vector of the real-time operation data is obtained as the prototype feature vector of the device to be monitored, which is a precondition for further judging whether the device to be monitored is in a normal operation state. The accuracy of judging the running state of the equipment to be monitored is improved.
In one embodiment, the calculating the similarity between the prototype feature vector and the high-dimensional feature vector of the real-time operation data, and obtaining the similarity value between the prototype feature vector and the high-dimensional feature vector of the real-time operation data includes:
and calculating Euclidean distance between the prototype feature vector and the high-dimensional feature vector of the real-time operation data, and taking the Euclidean distance as a similarity value between the prototype feature vector and the high-dimensional feature vector of the real-time operation data.
Specifically, the similarity value is a parameter for characterizing the degree of similarity between the high-dimensional feature vector of the real-time operation data and the prototype feature vector. The higher the similarity value, the closer is the prototype feature vector to the high-dimensional feature vector of the real-time running data; conversely, the lower the similarity value, the greater the gap between the prototype feature vector and the high-dimensional feature vector of the real-time operational data. There are various methods for calculating the similarity value, for example, euclidean distance, cosine similarity, or mahalanobis distance equidistant function values between the prototype feature vector and the high-dimensional feature vector of the real-time running data. In this embodiment, the similarity value between the prototype feature vector and the high-dimensional feature vector of the real-time operation data is obtained by calculating the euclidean distance between the two vectors.
In this embodiment, the euclidean distance between the prototype feature vector and the high-dimensional feature vector of the real-time operation data is calculated as the similarity value between the prototype feature vector and the high-dimensional feature vector of the real-time operation data, so that the operation state of the device to be monitored can be further monitored according to the similarity value, and the accuracy of monitoring the device to be monitored is improved.
In one embodiment, the determining whether the device to be monitored is malfunctioning based on the similarity value includes:
comparing the similarity value with a preset fault threshold value;
and if the similarity value exceeds the fault threshold value, judging that the equipment to be monitored is in a normal running state.
Specifically, after the similarity value between the prototype feature vector and the high-dimensional feature vector of the real-time operation data is obtained, the similarity value is also required to be compared with a preset fault threshold value, and the operation state of the equipment to be monitored is determined according to the comparison result. When the similarity value is higher than a preset fault threshold value, the prototype feature vector and the high-dimensional feature vector of the real-time operation data are closer to each other, and the operation state of the equipment to be monitored is normal. When the similarity value is lower than a preset fault threshold value, the difference between the prototype feature vector and the high-dimensional feature vector of the real-time operation data is larger, and the operation state of the equipment to be monitored is abnormal.
In this embodiment, by comparing the similarity value with a preset fault threshold, the difference between the similarity value and the preset fault threshold is used as a basis for judging the running state of the device to be monitored, so that the problem that the running data sample is generally less when the device to be monitored breaks down in the prior art, which results in that the fault judgment model generated by training generally has lower accuracy is solved, and the accuracy of fault monitoring of the device to be monitored is improved.
In one embodiment, the determining whether the device to be monitored is malfunctioning based on the similarity value further includes:
and if the similarity value does not exceed the fault threshold value, judging that the equipment to be monitored is in an abnormal operation state.
Specifically, when the similarity value is lower than a preset fault threshold value, the difference between the prototype feature vector and the high-dimensional feature vector of the real-time operation data is larger, so that the probability of occurrence of abnormality when the equipment to be monitored is operated is larger, and the operation state of the equipment to be monitored is judged to be abnormal.
In this embodiment, by comparing the similarity value with a preset fault threshold, the difference between the similarity value and the preset fault threshold is used as a basis for judging the running state of the device to be monitored, so that the problem that the running data sample is generally less when the device to be monitored breaks down in the prior art, which results in that the fault judgment model generated by training generally has lower accuracy is solved, and the accuracy of fault monitoring of the device to be monitored is improved.
In one embodiment, the determining that the device to be monitored is in an abnormal operation state further includes:
and sending the abnormal information of the equipment to be monitored to operation and maintenance personnel, and simultaneously sending out an abnormal alarm.
Specifically, after the operation state of the equipment to be monitored is determined according to the similarity value between the prototype feature vector and the high-dimensional feature vector of the real-time operation data and the preset fault threshold value, if the equipment to be monitored is in the abnormal operation state, the abnormal information of the equipment to be monitored is required to be sent to operation and maintenance personnel, and an abnormal alarm is sent. The abnormal information of the equipment to be monitored is sent to operation and maintenance personnel in a mode of short message, system prompt and the like; the abnormal alarm can be by means of a buzzer, a system alarm and the like.
In this embodiment, by sending the abnormal information to the operation and maintenance personnel and sending an alarm to the device to be monitored, which is determined to be in an abnormal state, the operation and maintenance personnel can be prompted for the abnormal information of the operation of the device to be monitored, so that the operation and maintenance personnel can acquire the operation abnormal information of the device to be monitored in time.
It should be understood that, although the steps in the flowcharts of fig. 2-4 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 2-4 may include multiple steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor does the order in which the steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of the steps or stages in other steps or other steps.
In one embodiment, as shown in fig. 6, there is provided an apparatus for monitoring a device failure, including: a first acquisition module 601, a second acquisition module 602, a third acquisition module 603, and a fault monitoring module 604, wherein:
the first obtaining module 601 is configured to input real-time operation data of a device to be monitored into a preset feature extraction network, and obtain a high-dimensional feature vector of the real-time operation data; the feature extraction network is obtained based on sample operation data and high-dimensional feature vector training corresponding to the sample operation data;
a second obtaining module 602, configured to obtain a prototype feature vector of the device to be monitored according to the high-dimensional feature vector of the real-time operation data; the prototype feature vector is a mean value of normal operation data of the equipment to be monitored, which is expressed in the form of a high-dimensional vector;
a third obtaining module 603, configured to perform similarity calculation on the prototype feature vector and the high-dimensional feature vector of the real-time operation data, to obtain a similarity value between the prototype feature vector and the high-dimensional feature vector of the real-time operation data;
and the fault monitoring module 604 is configured to determine whether the device to be monitored has a fault based on the similarity value.
In one embodiment, the first obtaining module 601 is further configured to: acquiring operation data of the equipment to be monitored in normal operation within a preset time period, and taking the operation data as sample operation data; extracting features of the sample operation data to obtain a high-dimensional feature vector corresponding to the sample operation data; and training a cyclic neural network model by taking the sample operation data and the high-dimensional feature vector corresponding to the sample operation data as a training set to obtain a feature extraction network.
In one embodiment, the second obtaining module 602 is further configured to: and acquiring a median or average value of the high-dimensional feature vector of the real-time operation data as a prototype feature vector of the equipment to be monitored.
In one embodiment, the third processing module 603 is further configured to: and calculating Euclidean distance between the prototype feature vector and the high-dimensional feature vector of the real-time operation data, and taking the Euclidean distance as a similarity value between the prototype feature vector and the high-dimensional feature vector of the real-time operation data.
In one embodiment, the fault monitoring module 604 is further configured to: comparing the similarity value with a preset fault threshold value; and if the similarity value exceeds the fault threshold value, judging that the equipment to be monitored is in a normal running state.
In one embodiment, the fault monitoring module 604 is further configured to: and if the similarity value does not exceed the fault threshold value, judging that the equipment to be monitored is in an abnormal operation state.
In one embodiment, the fault monitoring module 604 is further configured to: and sending the abnormal information of the equipment to be monitored to operation and maintenance personnel, and simultaneously sending out an abnormal alarm.
According to the equipment fault monitoring device, the high-dimensional feature vector of the real-time operation data of the equipment to be monitored is obtained through the preset feature extraction network, the prototype feature vector of the equipment to be monitored is obtained according to the high-dimensional feature vector of the real-time operation data, the similarity value between the high-dimensional feature vector of the real-time operation data and the prototype feature vector is finally obtained, and whether the equipment to be monitored breaks down is judged based on the similarity value. Compared with the monitoring of the equipment to be monitored by taking the data generated by the training of the training set as the fault judgment model, the prediction accuracy in fault monitoring is improved.
For specific limitations on the device fault monitoring apparatus, reference may be made to the above limitations on the device fault monitoring method, and no further description is given here. The above-described respective modules in the device failure monitoring apparatus may be implemented in whole or in part by software, hardware, and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 7. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing device fault monitoring data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a device fault monitoring method.
It will be appreciated by those skilled in the art that the structure shown in fig. 7 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:
inputting real-time operation data of equipment to be monitored into a preset feature extraction network, and obtaining a high-dimensional feature vector of the real-time operation data; the feature extraction network is obtained based on sample operation data and high-dimensional feature vector training corresponding to the sample operation data;
obtaining a prototype feature vector of the equipment to be monitored according to the high-dimensional feature vector of the real-time operation data; the prototype feature vector is a mean value of normal operation data of the equipment to be monitored, which is expressed in the form of a high-dimensional vector;
performing similarity calculation on the prototype feature vector and the high-dimensional feature vector of the real-time operation data to obtain a similarity value between the prototype feature vector and the high-dimensional feature vector of the real-time operation data;
and judging whether the equipment to be monitored has faults or not based on the similarity value.
In one embodiment, the processor when executing the computer program further performs the steps of: acquiring operation data of the equipment to be monitored in normal operation within a preset time period, and taking the operation data as sample operation data; extracting features of the sample operation data to obtain a high-dimensional feature vector corresponding to the sample operation data; and training a cyclic neural network model by taking the sample operation data and the high-dimensional feature vector corresponding to the sample operation data as a training set to obtain a feature extraction network.
In one embodiment, the processor when executing the computer program further performs the steps of: and acquiring a median or average value of the high-dimensional feature vector of the real-time operation data as a prototype feature vector of the equipment to be monitored.
In one embodiment, the processor when executing the computer program further performs the steps of: and calculating Euclidean distance between the prototype feature vector and the high-dimensional feature vector of the real-time operation data, and taking the Euclidean distance as a similarity value between the prototype feature vector and the high-dimensional feature vector of the real-time operation data.
In one embodiment, the processor when executing the computer program further performs the steps of: comparing the similarity value with a preset fault threshold value; and if the similarity value exceeds the fault threshold value, judging that the equipment to be monitored is in a normal running state.
In one embodiment, the processor when executing the computer program further performs the steps of: and if the similarity value does not exceed the fault threshold value, judging that the equipment to be monitored is in an abnormal operation state.
In one embodiment, the processor when executing the computer program further performs the steps of: and sending the abnormal information of the equipment to be monitored to operation and maintenance personnel, and simultaneously sending out an abnormal alarm.
According to the computer equipment, the high-dimensional feature vector of the real-time operation data of the equipment to be monitored is obtained through the preset feature extraction network, the prototype feature vector of the equipment to be monitored is obtained according to the high-dimensional feature vector of the real-time operation data, the similarity value between the high-dimensional feature vector of the real-time operation data and the prototype feature vector is finally obtained, and whether the equipment to be monitored fails or not is judged based on the similarity value. Compared with the monitoring of the equipment to be monitored by taking the data generated by the training of the training set as the fault judgment model, the prediction accuracy in fault monitoring is improved.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
inputting real-time operation data of equipment to be monitored into a preset feature extraction network, and obtaining a high-dimensional feature vector of the real-time operation data; the feature extraction network is obtained based on sample operation data and high-dimensional feature vector training corresponding to the sample operation data;
obtaining a prototype feature vector of the equipment to be monitored according to the high-dimensional feature vector of the real-time operation data; the prototype feature vector is a mean value of normal operation data of the equipment to be monitored, which is expressed in the form of a high-dimensional vector;
performing similarity calculation on the prototype feature vector and the high-dimensional feature vector of the real-time operation data to obtain a similarity value between the prototype feature vector and the high-dimensional feature vector of the real-time operation data;
and judging whether the equipment to be monitored has faults or not based on the similarity value.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring operation data of the equipment to be monitored in normal operation within a preset time period, and taking the operation data as sample operation data; extracting features of the sample operation data to obtain a high-dimensional feature vector corresponding to the sample operation data; and training a cyclic neural network model by taking the sample operation data and the high-dimensional feature vector corresponding to the sample operation data as a training set to obtain a feature extraction network.
In one embodiment, the computer program when executed by the processor further performs the steps of: and acquiring a median or average value of the high-dimensional feature vector of the real-time operation data as a prototype feature vector of the equipment to be monitored.
In one embodiment, the computer program when executed by the processor further performs the steps of: and calculating Euclidean distance between the prototype feature vector and the high-dimensional feature vector of the real-time operation data, and taking the Euclidean distance as a similarity value between the prototype feature vector and the high-dimensional feature vector of the real-time operation data.
In one embodiment, the computer program when executed by the processor further performs the steps of: comparing the similarity value with a preset fault threshold value; and if the similarity value exceeds the fault threshold value, judging that the equipment to be monitored is in a normal running state.
In one embodiment, the computer program when executed by the processor further performs the steps of: and if the similarity value does not exceed the fault threshold value, judging that the equipment to be monitored is in an abnormal operation state.
In one embodiment, the computer program when executed by the processor further performs the steps of: and sending the abnormal information of the equipment to be monitored to operation and maintenance personnel, and simultaneously sending out an abnormal alarm.
The storage medium acquires the high-dimensional feature vector of the real-time operation data of the equipment to be monitored through the preset feature extraction network, acquires the prototype feature vector of the equipment to be monitored according to the high-dimensional feature vector of the real-time operation data, finally acquires the similarity value between the high-dimensional feature vector of the real-time operation data and the prototype feature vector, and judges whether the equipment to be monitored has faults or not based on the similarity value. Compared with the monitoring of the equipment to be monitored by taking the data generated by the training of the training set as the fault judgment model, the prediction accuracy in fault monitoring is improved.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, or the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.
Claims (10)
1. A method of equipment fault monitoring, the method comprising:
inputting real-time operation data of equipment to be monitored into a preset feature extraction network, and obtaining a high-dimensional feature vector of the real-time operation data; the feature extraction network is obtained based on sample operation data and high-dimensional feature vector training corresponding to the sample operation data; the equipment to be monitored comprises power distribution equipment, high-low voltage equipment and control equipment; the real-time operation data comprise voltage values and current values of equipment to be monitored during operation, and the temperature and the environmental humidity of the equipment to be monitored, which are obtained through various sensors;
obtaining a prototype feature vector of the equipment to be monitored according to the high-dimensional feature vector of the real-time operation data; the prototype feature vector is a mean value of normal operation data of the equipment to be monitored, which is expressed in the form of a high-dimensional vector;
performing similarity calculation on the prototype feature vector and the high-dimensional feature vector of the real-time operation data to obtain a similarity value between the prototype feature vector and the high-dimensional feature vector of the real-time operation data;
judging whether the equipment to be monitored has faults or not based on the similarity value;
the feature extraction network is obtained by the following method:
acquiring operation data of the equipment to be monitored in normal operation within a preset time period, and taking the operation data as sample operation data;
extracting features of the sample operation data to obtain a high-dimensional feature vector corresponding to the sample operation data;
taking the sample operation data and the high-dimensional feature vector corresponding to the sample operation data as a training set, training a cyclic neural network model, and obtaining a feature extraction network;
the obtaining the prototype feature vector of the device to be monitored according to the high-dimensional feature vector of the real-time operation data comprises the following steps:
and acquiring a median or average value of the high-dimensional feature vector of the real-time operation data as a prototype feature vector of the equipment to be monitored.
2. The method of claim 1, wherein performing similarity calculation on the prototype feature vector and the high-dimensional feature vector of the real-time operation data, and obtaining a similarity value between the prototype feature vector and the high-dimensional feature vector of the real-time operation data comprises:
and calculating Euclidean distance between the prototype feature vector and the high-dimensional feature vector of the real-time operation data, and taking the Euclidean distance as a similarity value between the prototype feature vector and the high-dimensional feature vector of the real-time operation data.
3. The method of claim 1, wherein the determining whether the device to be monitored is malfunctioning based on the similarity value comprises:
comparing the similarity value with a preset fault threshold value;
and if the similarity value exceeds the fault threshold value, judging that the equipment to be monitored is in a normal running state.
4. The method of claim 3, wherein the determining whether the device to be monitored is malfunctioning based on the similarity value further comprises:
and if the similarity value does not exceed the fault threshold value, judging that the equipment to be monitored is in an abnormal operation state.
5. The method of claim 4, wherein the determining that the device to be monitored is in an abnormal operating state further comprises:
and sending the abnormal information of the equipment to be monitored to operation and maintenance personnel, and simultaneously sending out an abnormal alarm.
6. An equipment failure monitoring apparatus, the apparatus comprising:
the first acquisition module is used for inputting real-time operation data of the equipment to be monitored into a preset feature extraction network to acquire a high-dimensional feature vector of the real-time operation data; the feature extraction network is obtained based on sample operation data and high-dimensional feature vector training corresponding to the sample operation data; the equipment to be monitored comprises power distribution equipment, high-low voltage equipment and control equipment; the real-time operation data comprise voltage values and current values of equipment to be monitored during operation, and the temperature and the environmental humidity of the equipment to be monitored, which are obtained through various sensors;
the second acquisition module is used for acquiring the prototype feature vector of the equipment to be monitored according to the high-dimensional feature vector of the real-time operation data; the prototype feature vector is a mean value of normal operation data of the equipment to be monitored, which is expressed in the form of a high-dimensional vector;
the third acquisition module is used for carrying out similarity calculation on the prototype feature vector and the high-dimensional feature vector of the real-time operation data to acquire a similarity value between the prototype feature vector and the high-dimensional feature vector of the real-time operation data;
the fault monitoring module is used for judging whether the equipment to be monitored has faults or not based on the similarity value;
the first acquisition module is further used for acquiring operation data of the equipment to be monitored in normal operation within a preset time period, and the operation data is used as sample operation data; extracting features of the sample operation data to obtain a high-dimensional feature vector corresponding to the sample operation data; taking the sample operation data and the high-dimensional feature vector corresponding to the sample operation data as a training set, training a cyclic neural network model, and obtaining a feature extraction network;
the second obtaining module is further configured to obtain a median or average value of the high-dimensional feature vector of the real-time operation data, where the median or average value is used as a prototype feature vector of the device to be monitored.
7. The apparatus of claim 6, wherein the device comprises a plurality of sensors,
the third obtaining module is further configured to calculate a euclidean distance between the prototype feature vector and a high-dimensional feature vector of the real-time operation data, and use the euclidean distance as a similarity value between the prototype feature vector and the high-dimensional feature vector of the real-time operation data.
8. The apparatus of claim 6, wherein the device comprises a plurality of sensors,
the fault monitoring module is further used for comparing the similarity value with a preset fault threshold value; and if the similarity value exceeds the fault threshold value, judging that the equipment to be monitored is in a normal running state.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 5 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110712688.6A CN113570473B (en) | 2021-06-25 | 2021-06-25 | Equipment fault monitoring method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110712688.6A CN113570473B (en) | 2021-06-25 | 2021-06-25 | Equipment fault monitoring method, device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113570473A CN113570473A (en) | 2021-10-29 |
| CN113570473B true CN113570473B (en) | 2024-02-09 |
Family
ID=78162770
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110712688.6A Active CN113570473B (en) | 2021-06-25 | 2021-06-25 | Equipment fault monitoring method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113570473B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116541251B (en) * | 2023-07-04 | 2023-10-20 | 天津通信广播集团有限公司 | Display device state early warning method, device, equipment and computer readable medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008269063A (en) * | 2007-04-17 | 2008-11-06 | Softopia Japan Foundation | Device, method, and program for detecting abnormal action by using multiplex division image |
| CN104504400A (en) * | 2015-01-08 | 2015-04-08 | 中国科学院重庆绿色智能技术研究院 | Detection method of driver's abnormal behavior modeled based on online behavior |
| CN106886213A (en) * | 2017-03-13 | 2017-06-23 | 北京化工大学 | A kind of batch process fault detection method based on core similarity Support Vector data description |
| CN108844735A (en) * | 2018-06-22 | 2018-11-20 | 上海电力学院 | Epicyclic gearbox fault detection method based on convolution coder and Min formula distance |
| JP2019159729A (en) * | 2018-03-12 | 2019-09-19 | 株式会社リコー | Failure prediction system |
| WO2020113694A1 (en) * | 2018-12-04 | 2020-06-11 | 深圳码隆科技有限公司 | Spinning machine fault monitoring method and apparatus, and server |
| EP3719711A2 (en) * | 2020-07-30 | 2020-10-07 | Institutul Roman De Stiinta Si Tehnologie | Method of detecting anomalous data, machine computing unit, computer program |
| CN111767783A (en) * | 2020-04-22 | 2020-10-13 | 杭州海康威视数字技术股份有限公司 | Behavior detection method, behavior detection device, model training method, model training device, electronic equipment and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9984334B2 (en) * | 2014-06-16 | 2018-05-29 | Mitsubishi Electric Research Laboratories, Inc. | Method for anomaly detection in time series data based on spectral partitioning |
| CN110322048B (en) * | 2019-05-31 | 2023-09-26 | 南京航空航天大学 | Fault early warning method for production logistics conveying equipment |
-
2021
- 2021-06-25 CN CN202110712688.6A patent/CN113570473B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008269063A (en) * | 2007-04-17 | 2008-11-06 | Softopia Japan Foundation | Device, method, and program for detecting abnormal action by using multiplex division image |
| CN104504400A (en) * | 2015-01-08 | 2015-04-08 | 中国科学院重庆绿色智能技术研究院 | Detection method of driver's abnormal behavior modeled based on online behavior |
| CN106886213A (en) * | 2017-03-13 | 2017-06-23 | 北京化工大学 | A kind of batch process fault detection method based on core similarity Support Vector data description |
| JP2019159729A (en) * | 2018-03-12 | 2019-09-19 | 株式会社リコー | Failure prediction system |
| CN108844735A (en) * | 2018-06-22 | 2018-11-20 | 上海电力学院 | Epicyclic gearbox fault detection method based on convolution coder and Min formula distance |
| WO2020113694A1 (en) * | 2018-12-04 | 2020-06-11 | 深圳码隆科技有限公司 | Spinning machine fault monitoring method and apparatus, and server |
| CN111767783A (en) * | 2020-04-22 | 2020-10-13 | 杭州海康威视数字技术股份有限公司 | Behavior detection method, behavior detection device, model training method, model training device, electronic equipment and storage medium |
| EP3719711A2 (en) * | 2020-07-30 | 2020-10-07 | Institutul Roman De Stiinta Si Tehnologie | Method of detecting anomalous data, machine computing unit, computer program |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113570473A (en) | 2021-10-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10452845B2 (en) | Generic framework to detect cyber threats in electric power grid | |
| EP3373552A1 (en) | Multi-modal, multi-disciplinary feature discovery to detect cyber threats in electric power grid | |
| CN111210024A (en) | Model training method and device, computer equipment and storage medium | |
| CN111047082A (en) | Early warning method and device for equipment, storage medium and electronic device | |
| Mousavi et al. | Detecting incipient faults via numerical modeling and statistical change detection | |
| CN111524118B (en) | Running state detection method and device of transformer, computer equipment and storage medium | |
| CN112884199B (en) | Hydropower station equipment fault prediction method, hydropower station equipment fault prediction device, computer equipment and storage medium | |
| CN113093985B (en) | Sensor data link abnormity detection method and device and computer equipment | |
| CN115563873A (en) | Digital twin simulation system and method of power network | |
| CN117169761A (en) | Battery state evaluation method, apparatus, device, storage medium, and program product | |
| CN117031182B (en) | Method and system for detecting abnormal telemetering value of substation terminal | |
| CN117289085A (en) | Multi-line fault analysis and diagnosis method and system | |
| CN113570473B (en) | Equipment fault monitoring method, device, computer equipment and storage medium | |
| CN117031201A (en) | Multi-scene topology anomaly identification method and system for power distribution network | |
| CN113758652B (en) | Oil leakage detection method and device for converter transformer, computer equipment and storage medium | |
| CN113487182B (en) | Device health state evaluation method, device, computer device and medium | |
| CN117110794A (en) | Intelligent diagnosis system and method for cable faults | |
| CN113784235B (en) | Cable current-carrying capacity monitoring system, method, device, gateway equipment and storage medium | |
| CN115146727A (en) | Intelligent power utilization system fault detection method and system | |
| Tingting et al. | Early warning method for power station auxiliary failure considering large-scale operating conditions | |
| CN110232482B (en) | Equipment management method and device based on neural network | |
| CN115829543B (en) | Method for determining validity of preventive test of power equipment based on fault detection interval | |
| CN116381419B (en) | Transmission line fault processing method, device, computer equipment and storage medium | |
| CN116886735B (en) | Hydropower station operation monitoring system based on double star-type Ethernet structure | |
| CN118195583A (en) | State analysis method and device for intelligent operation and maintenance charging equipment parts |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |